-
Notifications
You must be signed in to change notification settings - Fork 608
Quantization types #4094
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Quantization types #4094
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/4094
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 1 Cancelled Job, 1 Unrelated FailureAs of commit 6beacf3 with merge base 561c035 ( CANCELLED JOB - The following job was cancelled. Please retry:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
@digantdesai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Rebase please? |
In order to support quantization to different types then int8 keep track of the limits and type as well. Signed-off-by: Per Åstrand <[email protected]> Change-Id: Ia5861adfeff4d57676ff06ccf5a7a8213c34efe6
Move away from implicitly assuming arguments are torch.int8 and figure out the type from the quantization nodes instead. This is done to prepare for breaking up the TOSA conversion and serialization into separate parts. Signed-off-by: Per Åstrand <[email protected]> Change-Id: Id88ef8f264e6af8e90a92a00fca13cdbcc857bab
@digantdesai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
@digantdesai merged this pull request in 074a81e. |
No description provided.